© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12377
    Prev
    Next
    INDEX
    Explanations

    -> symbols

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is strongly activated by website UI navigation elements—breadcrumb paths, menu labels, and interface command names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    টিও
    0.59
    リーナ
    0.59
    টুকু
    0.55
    ணய
    0.55
     बताए
    0.54
    咐
    0.54
    嚣
    0.54
    偣
    0.54
    毫不
    0.53
    ものです
    0.53
    POSITIVE LOGITS
     =>
    3.41
     →
    3.39
     ->
    3.36
     ==>
    3.17
     -->
    3.11
     ⇒
    3.06
    →
    3.03
    =>
    2.94
     --->
    2.94
    ⇒
    2.80
    Activations Density 0.084%

    No Known Activations